From 4dd863ecb5e399a6245b91290159a1e62585dbdf Mon Sep 17 00:00:00 2001
From: Richard Loyer <richard.loyer@c42.lu>
Date: Sun, 24 May 2026 14:49:39 +0200
Subject: [PATCH] Verdict: GDN HTP decode-only (2284), prefill GDN fallback CPU
 = ancre. B chiffre.

---
 CLAUDE.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/CLAUDE.md b/CLAUDE.md
index d357a5b..ae9351c 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -43,3 +43,6 @@ GGUF/llama.cpp archivés vers `/opt/Kazeia/to_delete`. Git local: commits régul
 
 ## Mesures 24/05 (build f0fe1058b, Pad3, Q4_0)
 prefill HTP pp128=44 / decode CPU tg16=13.4 ; HTP decode=4.4, CPU prefill pp32=18.5. → split prefill-HTP/decode-CPU OK, qwen35_compile HTP fonctionne. cli boucle (76min/0tok) — bench OK. Cible: pousser prefill 44→. Staging tablette: /data/local/tmp/kz-engine.
+
+## Verdict 24/05 (mesure honnête, pp égal)
+prefill pp32/128/512: CPU 18.5/18.7/18.7 (PLAT), HTP 18.5/44/47. HTP ×2.5 reel a pp512. GDN HTP = decode-only (ggml-hexagon.cpp:2284 "n_tokens!=1 -> CPU fallback"). Prefill GDN sur CPU serie = ancre. Kernel GDN-prefill chunked HTP = le sujet B, gros gain (FA/FFN HTP pourraient ~159). cli boucle = bug runtime aval, PAS compile (bench=meme graphe). Decode tranche, prefill = chantier.